Investigating the capabilities of evolutionary data-driven techniques using the challenging estimation of soil moisture content

摘要

Soil moisture has a crucial role in both the global energy and hydrological cycles; it affectsndifferent ecosystem processes. Spatial and temporal variability of soil moisture add to its complexnbehaviour, which undermines the reliability of most current measurement methods. In this paper,ntwo promising evolutionary data-driven techniques, namely (i) Evolutionary Polynomial Regressionnand (ii) Genetic Programming, are challenged with modelling the soil moisture response to thennear surface atmospheric conditions. The utility of the proposed models is demonstrated throughnthe prediction of the soil moisture response of three experimental soil covers, used for thenrestoration of watersheds that were disturbed by the mining industry. The results showed thatnthe storage effect of the soil moisture response is the major challenging factor; it can benquantified using cumulative inputs better than time-lag inputs, which can be attributed to theneffect of the soil layer moisture-holding capacity. This effect increases with the increase in thensoil layer thickness. Three different modelling tools are tested to investigate the tool effect inndata-driven modelling. Despite the promising results with regard to the prediction accuracy, thenstudy demonstrates the need for adopting multiple data-driven modelling techniques and toolsn(modelling environments) to obtain reliable predictions.